Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Is the quantitative result suit to the result reported in the paper? #1

Closed
minygd opened this issue Aug 17, 2019 · 4 comments
Closed

Comments

@minygd
Copy link

minygd commented Aug 17, 2019

Hello! Thanks for your reimplement of the Omnidepth. There is a confusion for me, that is, is the quantitave result and qualitative result performs well just as the author stated in the paper?

Or is there any difference? Can you show some result of your model?

Thx!

@meder411
Copy link
Owner

meder411 commented Aug 17, 2019

These results are commensurate with those reported in the paper. If I have some time, I will run the eval script and post some specifics in the README.

@minygd
Copy link
Author

minygd commented Aug 17, 2019

Thank you. :)

By the way, I have some problem while running the codes.
I have installed OpenEXR by commend: pip install OpenEXR.
But it turned out I missed something:

/.local/lib/python3.7/site-packages/OpenEXR.cpython-37m-x86_64-linux-gnu.so: undefined symbol: _ZTIN7Iex_2_27BaseExcE

Can you give me some suggestions? Thx!

@meder411
Copy link
Owner

Use the conda environment as explained in the README

@minygd
Copy link
Author

minygd commented Aug 18, 2019

Yes, I wanted to just set up a conda environment using the omnidepth.yml file in this repository, but the conda install informed me that there are some pkgs missing or can't be found. So I end up using conda and pip to install all the pkgs by hand.

@minygd minygd closed this as completed Aug 18, 2019
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants